AU2012227156C1 - A method of selecting a device for delivering a recommendation - Google Patents

Abstract

-24 Abstract A METHOD OF SELECTING A DEVICE FOR DELIVERING FOR DELIVERING A RECOMMENDATION A method (600) of selecting an electronic device (e.g., 101) for delivering a recommendation, is disclosed. A preference rating is received for each of a plurality of electronic devices based on a task to be recommended, each of the preference ratings defining preference of a user for receiving the recommendation on a corresponding one of the electronic devices (e.g., 101). A timeliness profile associated with the recommendation is received. The timeliness profile defines relevance of delivering the recommendation over a period of time. One of the electronic devices (e.g., 101) on which to deliver the recommendation at a particular point in time is selected based on the preference rating of the selected electronic device and the timeliness profile associated with the recommendation. 670914vl (PO42054_SpeciAs Filed) -3/9 LOa) 0) 0 C: a) -o CIO > a)) 0) D> (0 0 -0 a) _0 c8 a) -0 679371 P0254DrwngA lid

Description

- 1 - 2012227156 17 Sep 2012

A METHOD OF SELECTING A DEVICE FOR DELIVERING A RECOMMENDATION

FIELD OF INVENTION

The current invention relates generally to delivery of recommendations and, in particular, the suitability of a recommendation to be delivered to an electronic device. The present invention also relates to a method and apparatus for selecting a device for delivering a recommendation, and to a computer program product including a computer readable medium having recorded thereon a computer program for selecting a device for delivering a recommendation.

DESCRIPTION OF BACKGROUND ART ) Recommendation has become a common feature in many electronic devices and other systems. When there are a multitude of choices available to a user or when a user is unaware of the availability of potentially desirable goods and services, a recommendation system can be a useful tool for the user by bringing relevant choices to the attention of the user. Thus, a lot of time and effort can be saved by the user in discovering individual choices. 5 Recommendation systems are commonly used by online retailers to generate purchase recommendations. Such recommendation systems are also used by media content providers to generate, for example, movie, music and news content recommendations. The recommendations are typically based on the user’s own past behaviours and other similar users’ past behaviours. Various degrees of personalisation may also be employed by a 20 recommendation system to relate a recommendation to a personal aspect of the user in order to increase the effectiveness of the recommendation. One example of such personalisation is the making of a recommendation for purchasing a gift for a loved one near a birthday of the loved one.

As the popularity of using various recommendation methods grows, the number of 25 recommendations targeting a user has also increased dramatically. A user may receive a recommendation on a number of devices available to the user, such as a mobile phone (e.g, a smart phone), tablet or personal computer (PC) in various forms such as an email, a notification on a mobile application or an advertisement on a web page. Often, these recommendations are presented to the user unsolicited, causing the user to perceive them as 670914V] (P042054_Speci_As Filed) -2- 2012227156 19 Jul2016 advertising spam, especially when the current environment or user’s mind-set is unsuitable to act upon a recommendation. Under such circumstances, a recommendation presented to the user may be ignored or, at best, the action required for the recommendation may be postponed. Any postponed recommendations may be forgotten by the user or the desire for utilising the 5 recommendations may wane before the user has a chance to follow-up on the recommended action. Such postponed recommendations can cause a low utilisation of recommendations even if the recommendations are relevant and appropriately personalised.

SUMMARY OF THE INVENTION

It is an object of the present invention to substantially overcome, or at least ameliorate, one 0 or more disadvantages of existing arrangements.

According to one aspect of the present disclosure there is provided a method of selecting an electronic device for delivering a recommendation, said method comprising: receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the 5 recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; receiving a timeliness profile associated with the recommendation, said timeliness profile defining a degree of relevance of delivering the recommendation with respect to an event over a period of time, the timeliness profile being stored in a second memory of the computer of 0 the computer device; selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the first memory and on a degree of relevance of delivering the recommendation with respect to the event at said particular point in time determined by retrieving the corresponding degree of 25 relevance from the second memory where the timeliness profile associated with the recommendation is stored.

According to another aspect of the present disclosure there is provided a system for selecting an electronic device for delivering a recommendation, said system comprising: a memory for storing data and a computer program; 30 a processor coupled to said memory for executing said computer program, said computer program comprising instructions for: receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the 11554944 -3 - 2012227156 19 Jul2016 recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; receiving a timeliness profile associated with the recommendation, said timeliness profile defining a degree of relevance of delivering the recommendation with respect to an event over 5 a period of time the timeliness profile being stored in a second memory of the computer device; selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the first memory and on a degree of relevance of delivering the recommendation with respect to the 0 event at said particular point in time determined by retrieving the corresponding degree of relevance from the second memory where the timeliness profile associated with the recommendation is stored.

According to still another aspect of the present disclosure there is provided an apparatus for selecting an electronic device for delivering a recommendation, said apparatus comprising: 5 means for receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; means for receiving a timeliness profile associated with the recommendation, said 0 timeliness profile defining a degree of relevance of delivering the recommendation with respect to an event over a period of time, the timeliness profile being stored in a second memory of the computer device; means for selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the 25 first memory and on a degree of relevance of delivering the recommendation with respect to the event at said particular point in time determined by retrieving the corresponding degree of relevance from the second memory where the timeliness profile associated with the recommendation is stored.

According to still another aspect of the present disclosure there is provided a computer 30 readable medium having a computer program stored thereon for selecting an electronic device for delivering a recommendation, said program: code for receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the 11554944 -4- 2012227156 19 Jul2016 recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; code for receiving a timeliness profile associated with the recommendation, said timeliness profile defining relevance of delivering the recommendation with respect to an event over a 5 period of time, the timeliness profile being stored in a second memory of the computer device; code for selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the first memory and on a degree of relevance of delivering the recommendation with respect to the event at said particular point in time determined by retrieving the corresponding degree of 0 relevance from the second memory where the timeliness profile associated with the recommendation is stored.

Other aspects of the invention are also disclosed.

BRIEF DESCRIPTION OF THE DRAWINGS 5 One or more embodiments of the invention will now be described with reference to the following drawings, in which:

Figs. 1A and IB collectively form a schematic block diagram representation of an electronic device upon which described arrangements can be practised;

Fig. 1C is a schematic block diagram of a software architecture for use with the described 0 arrangements;

Fig. 2 shows structure and example data of a usage profile;

Fig. 3 is a schematic flow diagram showing a method of determining a usage profile;

Fig. 4 shows an example of device preference structure and values;

Fig. 5A is a diagram showing an example timeliness profile; 25 Fig. 5B is a diagram showing another example timeliness profile;

Fig. 6 is a schematic flow diagram showing a method selecting an electronic device for delivering a recommendation; and

Fig. 7 is a diagram showing a graphical representation of suitability ratings and recommendation relevance in terms of time. 11554944 - 4a - 2012227156 19 Jul2016 DETAILED DESCRIPTION OF EMBODIMENTS OF THE INVENTION Where reference is made in any one or more of the accompanying drawings to steps and/or features, which have the same reference numerals, those steps and/or features have for the 5 purposes of this description the same function(s) or operation(s), unless the contrary intention appears. 11554944 -5- 2012227156 17 Sep 2012 A method 600 of selecting an electronic device for delivering a recommendation is described below with reference to Fig. 6. Figs. 1A and IB collectively form a schematic block diagram of a general purpose electronic device 101 including embedded components, upon which the described methods are desirably practiced. The electronic device 101 may be, for example, a mobile phone (e.g., smart phone), a portable media player, personal data assistant or a digital camera, in which processing resources are limited. Nevertheless, the methods to be described may also be performed on higher-level devices such as desktop computers, server computers, and other such devices with significantly larger processing resources. I As seen in Fig. 1A, the electronic device 101 comprises an embedded controller 102.

Accordingly, the electronic device 101 may be referred to as an “embedded device.” In the present example, the controller 102 has a processing unit (or processor) 105 which is bidirectionally coupled to an internal storage module 109. The storage module 109 may be formed from non-volatile semiconductor read only memory (ROM) 160 and semiconductor 5 random access memory (RAM) 170, as seen in Fig. IB. The RAM 170 may be volatile, nonvolatile or a combination of volatile and non-volatile memory.

The electronic device 101 includes a display controller 107, which is connected to a video display 114, such as a liquid crystal display (LCD) panel or the like. The display controller 107 is configured for displaying graphical images on the video display 114 in 0 accordance with instructions received from the embedded controller 102, to which the display controller 107 is connected.

The electronic device 101 also includes user input devices 113 which are typically formed by keys, a keypad or like controls. In some implementations, the user input devices 113 may include a touch sensitive panel physically associated with the display 114 to 25 collectively form a touch-screen. Such a touch-screen may thus operate as one form of graphical user interface (GUI) as opposed to a prompt or menu driven GUI typically used with keypad-display combinations. Other forms of user input devices may also be used, such as a microphone (not illustrated) for voice commands or a joystick/thumb wheel (not illustrated) for ease of navigation about menus. 30 As seen in Fig. 1A, the electronic device 101 also comprises a portable memory interface 106, which is coupled to the processor 105 via a connection 119. The portable memory interface 106 allows a complementary portable memory device 125 to be coupled to the electronic device 101 to act as a source or destination of data or to supplement the internal 670914vl (P042054_Speci_As Filed) -6- 2012227156 17 Sep 2012 storage module 109. Examples of such interfaces permit coupling with portable memory devices such as Universal Serial Bus (USB) memory devices, Secure Digital (SD) cards, Personal Computer Memory Card International Association (PCMIA) cards, optical disks and magnetic disks.

The electronic device 101 also has a communications interface 108 to permit coupling of the device 101 to a computer or communications network 120 via a connection 121. The connection 121 may be wired or wireless. For example, the connection 121 may be radio frequency or optical. An example of a wired connection includes Ethernet. Further, an example of wireless connection includes BluetoothTM type local interconnection, Wi-Fi ) (including protocols based on the standards of the IEEE 802.11 family), Infrared Data Association (IrDa) and the like.

Typically, the electronic device 101 is configured to perform some special function. The embedded controller 102, possibly in conjunction with further special function components 110, is provided to perform that special function. For example, where the device 5 101 is a digital camera, the components 110 may represent a lens, focus control and image sensor of the camera. The special function components 110 is connected to the embedded controller 102. As another example, the device 101 may be a mobile telephone handset. In this instance, the components 110 may represent those components required for communications in a cellular telephone environment. Where the device 101 is a portable 0 device, the special function components 110 may represent a number of encoders and decoders of a type including Joint Photographic Experts Group (JPEG), (Moving Picture

Experts Group) MPEG, MPEG-1 Audio Layer 3 (MP3), and the like.

The methods described hereinafter may be implemented using the embedded controller 102, where the processes of Figs. 2 to 7 may be implemented as one or more software 25 application programs 133 executable within the embedded controller 102. The electronic device 101 of Fig. 1A implements the described methods. In particular, with reference to Fig. IB, the steps of the described methods are effected by instructions in the software 133 that are carried out within the controller 102. The software instructions may be formed as one or more code modules, each for performing one or more particular tasks. The software may also be 30 divided into two separate parts, in which a first part and the corresponding code modules performs the described methods and a second part and the corresponding code modules manage a user interface between the first part and the user. 6709l4v I (P042054_Speci As Filed) -7- 2012227156 17 Sep 2012

The software 133 of the embedded controller 102 is typically stored in the non-volatile ROM 160 of the internal storage module 109. The software 133 stored in the ROM 160 can be updated when required from a computer readable medium. The software 133 can be loaded into and executed by the processor 105. In some instances, the processor 105 may execute software instructions that are located in RAM 170. Software instructions may be loaded into the RAM 170 by the processor 105 initiating a copy of one or more code modules from ROM 160 into RAM 170. Alternatively, the software instructions of one or more code modules may be pre-installed in a non-volatile region of RAM 170 by a manufacturer. After one or more code modules have been located in RAM 170, the processor 105 may execute software instructions of the one or more code modules.

The application program 133 is typically pre-installed and stored in the ROM 160 by a manufacturer, prior to distribution of the electronic device 101. However, in some instances, the application programs 133 may be supplied to the user encoded on one or more CD-ROM (not shown) and read via the portable memory interface 106 of Fig. 1A prior to storage in the ) internal storage module 109 or in the portable memory 125. In another alternative, the software application program 133 may be read by the processor 105 from the network 120, or loaded into the controller 102 or the portable storage medium 125 from other computer readable media. Computer readable storage media refers to any non-transitory tangible storage medium that participates in providing instructions and/or data to the controller 102 for 0 execution and/or processing. Examples of such storage media include floppy disks, magnetic tape, CD-ROM, a hard disk drive, a ROM or integrated circuit, USB memory, a magnetooptical disk, flash memory, or a computer readable card such as a PCMCIA card and the like, whether or not such devices are internal or external of the device 101. Examples of transitory or non-tangible computer readable transmission media that may also participate in the 25 provision of software, application programs, instructions and/or data to the device 101 include radio or infra-red transmission channels as well as a network connection to another computer or networked device, and the Internet or Intranets including e-mail transmissions and information recorded on Websites and the like. A computer readable medium having such software or computer program recorded on it is a computer program product. 30 The second part of the application programs 133 and the corresponding code modules mentioned above may be executed to implement one or more graphical user interfaces (GUIs) to be rendered or otherwise represented upon the display 114 of Fig. 1A. Through manipulation of the user input device 113 (e.g., the keypad), a user of the device 101 and the 670914V! (P042054_Speci_As Filed) -8- 2012227156 17 Sep 2012 application programs 133 may manipulate the interface in a functionally adaptable manner to provide controlling commands and/or input to the applications associated with the GUI(s). Other forms of functionally adaptable user interfaces may also be implemented, such as an audio interface utilizing speech prompts output via loudspeakers (not illustrated) and user voice commands input via the microphone (not illustrated).

Fig. IB illustrates in detail the embedded controller 102 having the processor 105 for executing the application programs 133 and the internal storage 109. The internal storage 109 comprises read only memory (ROM) 160 and random access memory (RAM) 170. The processor 105 is able to execute the application programs 133 stored in one or both of the ) connected memories 160 and 170. When the electronic device 101 is initially powered up, a system program resident in the ROM 160 is executed. The application program 133 permanently stored in the ROM 160 is sometimes referred to as “firmware”. Execution of the firmware by the processor 105 may fulfil various functions, including processor management, memory management, device management, storage management and user interface. 5 The processor 105 typically includes a number of functional modules including a control unit (CU) 151, an arithmetic logic unit (ALU) 152 and a local or internal memory comprising a set of registers 154 which typically contain atomic data elements 156, 157, along with internal buffer or cache memory 155. One or more internal buses 159 interconnect these functional modules. The processor 105 typically also has one or more interfaces 158 for 0 communicating with external devices via system bus 181, using a connection 161.

The application program 133 includes a sequence of instructions 162 though 163 that may include conditional branch and loop instructions. The program 133 may also include data, which is used in execution of the program 133. This data may be stored as part of the instruction or in a separate location 164 within the ROM 160 or RAM 170. 25 In general, the processor 105 is given a set of instructions, which are executed therein.

This set of instructions may be organised into blocks, which perform specific tasks or handle specific events that occur in the electronic device 101. Typically, the application program 133 waits for events and subsequently executes the block of code associated with that event. Events may be triggered in response to input from a user, via the user input devices 113 of 30 Fig. 1A, as detected by the processor 105. Events may also be triggered in response to other sensors and interfaces in the electronic device 101.

The execution of a set of the instructions may require numeric variables to be read and modified. Such numeric variables are stored in the RAM 170. The disclosed method uses 670914v 1 (P042054_Speci_As Filed) -9- 2012227156 17 Sep 2012 input variables 171 that are stored in known locations 172, 173 in the memory 170. The input variables 171 are processed to produce output variables 177 that are stored in known locations 178, 179 in the memory 170. Intermediate variables 174 may be stored in additional memory locations in locations 175, 176 of the memory 170. Alternatively, some intermediate variables may only exist in the registers 154 of the processor 105.

The execution of a sequence of instructions is achieved in the processor 105 by repeated application of a fetch-execute cycle. The control unit 151 of the processor 105 maintains a register called the program counter, which contains the address in ROM 160 or RAM 170 of the next instruction to be executed. At the start of the fetch execute cycle, the contents of the memory address indexed by the program counter is loaded into the control unit 151. The instruction thus loaded controls the subsequent operation of the processor 105, causing for example, data to be loaded from ROM memory 160 into processor registers 154, the contents of a register to be arithmetically combined with the contents of another register, the contents of a register to be written to the location stored in another register and so on. At the end of the fetch execute cycle the program counter is updated to point to the next instruction in the system program code. Depending on the instruction just executed this may involve incrementing the address contained in the program counter or loading the program counter with a new address in order to achieve a branch operation.

Each step or sub-process in the processes of the methods described below is associated ) with one or more segments of the application program 133, and is performed by repeated execution of a fetch-execute cycle in the processor 105 or similar programmatic operation of other independent processor blocks in the electronic device 101.

The described methods may be used to determine a time for delivering a recommendation to a user, where the user has access to multiple electronic devices for 25 personal use. As described above, the electronic devices available to the user may include, for example, a mobile phone (e.g., smart phone), a portable media player, personal data assistant, a digital camera or a personal computer (PC). The user may select to use one of the electronic devices (e.g., the device 101) over another based on current availability of the selected device, the type of activity the user is conducting or simply a personal preference. With the usage of 30 the multiple electronic devices by the user over time, a usage profile of the electronic devices may be determined to show a regular pattern of when the user uses which of the multiple devices. 670914VI (P042054_Speci_As Filed) -10- 2012227156 17 Sep 2012 A recommendation may be associated with a task and the task may be associated with preference for a type of device for performing the task. For example, a recommendation for creating a photo-book for the birthday of a friend requires the user to perform a photo book creation task and the preferred devices for the task may be the personal computer, followed by the tablet, etc. A recommendation may be time sensitive such that the relevance of the recommendation to the user is a function of time. For example, the relevance of the photo book recommendation described above increases towards the date of the birthday. Further, the relevance of the photo book recommendation quickly diminishes when a current time gets too I close to the date of the birthday to make the photo book, since making the photo book usually requires a reasonable amount effort from the user and a period of several days for production and shipping after an order is placed.

The described methods profile a usage pattern for the multiple devices available to the user. The described methods also determine a time for delivering a time-sensitive 5 recommendation to one of the devices. The time for delivering the recommendation is determined based on whether the user will find the recommendation relevant and whether the device receiving the recommendation is suitable for performing the task associated with the recommendation.

Fig. 1C is a schematic diagram showing a software architecture 190 for use in the 0 described methods. In the example of Fig. 1C, the user has access to multiple electronic devices 101-A, 101 -B, 101-C and 101-D. The device 101-B is a tablet computer, the device 101-C is a smart phone and the device 101-D is a digital camera. Each of the devices 101-B, 101 -C and 101-D are configured as described above with reference to Figs. 1A and IB, with each of the devices 101-B, 101-C and 101-D having a corresponding processor 105, storage 25 module 109, display device 114 as well as the other components described above with reference to Figs. 1A and IB. Further, the device 101-A is a personal computer (PC), which again has a similar configuration to the other devices 101-B, 101-C, 101-D, albeit in the form of a PC. The electronic devices 101-A, 101-B, 101-C and 101-D will be referred to generically below as the electronic devices 101 unless one of the devices 101-A, 101-B, 101-30 C and 101-D is referred to specifically. The software architecture 190 comprises software code modules 191, 194 and 196 as described below, which may form part of the software application program 133. 670914v I (P042054_Speci_As Filed) -11 - 2012227156 17 Sep 2012

As seen in Fig. 1C, a usage profiler module 196 examines patterns in usage history of the electronic devices 101 and constructs a usage profile 192 of the user using the electronic devices 101. The usage profiler module 196 may be configured for capturing the usage history of the electronic devices 101 from the storage module 109, for example. The usage profile 192 is determined from previously captured usage history. A recommendation engine module 191 generates recommendations 193 for the user. The generated recommendations 193 may be used, for example, to create a personalised photo merchandise product.

Any suitable method may be used by the recommendation module 191 for generating ) the recommendations 193. Typically, such methods involve a combination of following explicit preferences specified by the user, analysing the past behaviours of the user to predict future behaviours and using collaborative filtering methods to predict behaviours of the user based on other similar users.

Each generated recommendation 193 is associated with a device preference 197 5 indicating preferred electronic devices for receiving the recommendation 193 and a timeliness profile 195 that defines relevance of a recommendation 193 as a function of time. As described below, the timeliness profile 195 defines changing relevance of delivering the recommendation 193 over a period of time. When the user starts using one of the devices 101 and when there is a recommendation 193 pending delivery, recommendation delivery module :0 194, under execution of the processor 105, determines if a current point in time is likely to be an appropriate time for delivering the recommendation 193. The recommendation delivery module 194 makes the determination based on the current device 101 being used, user preference for the current device 101 and the timeliness profile 195 of the recommendation 193 to be delivered. 25 If the current point in time is not appropriate, the recommendation delivery module 194 may determine that there is potentially a better time for delivering the recommendation 193. Again, the recommendation delivery module 194 makes the determination based on the usage profile 192 which may indicate a future use of this or another device 101 at a better time. 30 Each of the modules 191, 194 and 196 may be stored within the ROM 160 and be controlled in their execution by the processor 105 of the device 101. Similarly, the usage profile 192, recommendations 193, timeliness profile 195 and device preference 197 may be stored within the storage module 109. 670914VI (P042054_Speci_As Filed) - 12- 2012227156 17 Sep 2012 i

Fig. 2 shows an example of a usage profile 192. The usage profile 192 is a pattern of typical device usage sessions for the electronic devices 101 accessible to the user. As described in detail below, a particular cluster of one or more of the usage sessions is represented in the usage profile 192 by a particular device usage session record (e.g., 210). Each device usage record 210 may comprise the following fields: (i) SessionPeriod: time period of a typical usage session; (ii) DeviceType: type of device used in the session; and (iii) Probability: probability of the session happening. For example, the device usage session record 210 indicates that there is a 95% probability that the user will use the tablet device 101 -B between 7AM and 7:30AM next Monday.

The usage profile 192 enables the recommendation delivery module 194, under execution of the processor 105, to predict a likely usage of a particular device 101 in the future, which is a potential opportunity for delivering a recommendation 193. 5 Fig. 3 is a schematic flow diagram showing a method 300 of determining a usage profile. The method 300 may be implemented as one or more software code modules of the software application program 133 (e.g., the usage profiler module 196) resident in the ROM 160 and being controlled in its execution by the processor 105 of the device 101. The method 300 will be described by way of example where a record 210 of the usage profile 196 is 0 determined for the tablet electronic device 101-B. However, the steps 310 to 340 of the method 300 are executed for each of the electronic devices 101-A, 101-B, 101-C and 101-D. The method 300 determines the usage profile 192 from the analytics of collected device usage sessions.

The usage profile 192 determined in accordance with the method 300 includes the 25 information for three of the fields described above (i.e., Session Period, DeviceType and Probability). The determined usage profile 192 is configured for defining a measure of user interactions with each of the electronic devices 101-A, 101-B, 101-C and 101-D for a period of time.

The method 300 starts at collecting step 310, where the usage profiler 196, under 30 execution of the processor 105, clusters collected usage sessions based on time of the day and the day of the week (e.g., Monday, 0700-0730) for each of the electronic devices 101. Each resulting cluster corresponds to a regular behaviour of usage of a particular device by the user and is represented by a record (e.g., 210) created in the usage profile 192 stored within the 670914vl (P042054_Speci_As Filed) - 13 - 2012227156 17 Sep 2012 storage module 109. Each cluster is associated with the SessionPeriod field of the usage profile 192 stored within the storage module 109.

At mean time determining step 320, the sessions in each cluster are aggregated by the processor 105 to determine a mean time of the day and day of the week representative of the sessions in the cluster. As described above, each cluster is represented by a record (e.g., 210) created in the usage profile 192 stored within the storage module 109.

Then at probability determining step 330, the number of sessions in each cluster and the time period for collecting the analytics are used to determine probability of a similar session occurring in the future. The probability may be determined in accordance with ' Equation (1), as follows: probability = number of sessions in cluster / maximum number of sessions within time period. (1) ! For example, if there are forty (40) sessions in a cluster representative of a session where the user uses the tablet 101-B between 7AM and 7:30AM on work-day Mondays during a period of one year for collecting the analytics, the probability of such a session eventuating in the future is 40/52 = 87%.

At creating step 340, the usage profiler module 196, under execution of the processor ) 105, creates a record (e.g., 210) in the usage profile 192 for each significant cluster representing a typical regular usage of a particular electronic device 101 by the user. A particular cluster may be determined to be significant at step 340 if the determined probability is greater than 50%.

Fig. 4 shows an example of device preferences 197 associated with various types of 25 recommendations 193. The device preferences 197 associated with each type of recommendation is represented by a device preference record 410. Each device preference record 410 comprises a RecommendationType field which defines the type of recommendation that may be associated with a task. Each device preference record (e.g., 410) also comprises preference ratings in the form of percentage values corresponding to each type 30 of electronic device 101-A, 101-B, 101 -C and 101 -D. Each preference rating percentage value of a particular record 410 represents preference of the user for using the corresponding device (e.g., 101 A) for performing the task associated with the recommendation. Each of the preference rating percentage values of the device preferences also define preference of the 670914vl (P042054_Speci_As Filed) - 14- 2012227156 17 Sep 2012 user for receiving the recommendation on the corresponding device (e.g., 101 A). For example, as seen in Fig. 4, a photo book creation recommendation is preferred to be received and acted upon on the PC 101-A (i.e., preference rating = 100%), followed by the tablet device 101 -B (i.e., preference rating = 80%), smartphone 101-C (i.e., preference rating = 20%) and camera 101-D (i.e., preference rating = 0%). The device preference ratings represented by the percentage values may be determined from the user’s history of performing the particular type of task on the various electronic devices 101. The percentage of occurrences of using a particular device (e.g., 101-A) for a particular type of task may be used to correlate the preference for using the device 101-A for the type of task. For example, if the I user has created ten (10) photo books in the past, five on the PC 101-A, four on the tablet device 101-B and one on the smartphone device 101-C, then the percentages of occurrences for using the devices 101 will be 0.5, 0.4 and 0.1 respectively. Normalising the determined percentage values and using the normalised percentage values as device preferences yields 100%, 80% and 20% as in the record 410 shown in Fig. 4. > In another arrangement, if a new user has very little history in performing the tasks that may be associated with a recommendation, the percentage preference values for the record 410 may be determined as an average from other users.

Fig. 5A and Fig. 5B each show an example of a timeliness profile 195-1 and 195-2, respectively. Each of the timeliness profiles 195-1 and 195-2 graphs relevance as a function 3 of time to indicate relevance of a time-sensitive recommendation in terms of a particular point in time. A recommendation is usually time-sensitive if the recommendation is related to an event in time. Different relevance functions are required for different situations for delivering a recommendation. For example, the timeliness profile 195-1 shows a relevance function fora recommendation to prepare for an upcoming event such as a birthday. The date of the event is 25 t2. Accordingly, as seen in Fig. 5A, the relevance increases as the event is approaching and peaks at time t| which represents the point in time when the user must act on the recommendation. Acting on the recommendation may include the user starting to make a photo book for the birthday which occurs at time, t2. After time, t|, the relevance decreases rapidly as the user has missed the opportunity to utilise the recommendation for best effect. 30 Depending on the type of task associated with a recommendation, the time between time, 11, and time, t2, may vary according to the nature of the task. For example, the user is likely to require more time to act upon a recommendation for creating an expensive photo 670914v I (P042054_Speci_As Filed) - 15- 2012227156 17 Sep 2012 book to ensure that a best possible result is achieved compared to a recommendation to post a set of images to a social network.

As seen in Fig. 5B, the timeliness profile 195-2 represents a different relevance function for a situation when a recommendation is made for a user soon after an event. For example, the relevant function of Fig. 5B may apply to posting photographs taken at a party to a social network after the party. Time, t3, is the date of the party. The relevance of the task is at a maximum immediately after the party because the emotion from the event is still high. However, the relevance of the task decreases gradually over time as the emotion and interest for the event wanes.

In one arrangement, a set of timeliness profiles, including the profiles 195-1 and 195-2, may be predefined for a variety of situations and stored within the storage module 109 of the device 101. When a recommendation is generated by the recommendation engine module 191, the recommendation engine module 191 associates one of the predefined timeliness profiles 195 stored within the storage module 109 matching the situation for making the 5 recommendation to the generated recommendation.

The method 600 of selecting an electronic device 101 for delivering a recommendation is described below with reference to Fig. 6. The method 600 will be described by way of example with reference to the tablet device 101-B. The method 600 may be implemented as one or more software code modules of the software application program 133 (e.g., the 0 recommendation delivery module 196) resident in the ROM 160 of the table device 101-B and being controlled in its execution by the processor 105 of the tablet device 101-B. The method 600 determines if a current point in time is a good time for delivering a pending recommendation.

The method 600 starts at detecting step 610, where the recommendation delivery 25 module 194, under execution of the processor 105 of the tablet device 101-B, detects starting of a mobile application or logging on to a website indicating that the user has started a current session on one of the electronic devices 101. For example, a mobile application may be executed on the tablet device 101-B indicating that the user has started a current session on the tablet device 101-B. 30 At usage profile receiving step 620, the recommendation delivery module 194, under execution of the processor 105, receives the usage profile 192 of each of the electronic devices 101-A, 101-B, 101-C and 101 -D accessible to the user. The usage profiles 192 may be stored within the RAM 170 of the tablet device 101-B. 670914VI (P042054_Speci_As Filed) - 16- 2012227156 17 Sep 2012

Then at recommendation receiving step 630, the recommendation delivery module 194 receives a recommendation 193 generated by the recommendation engine module 191 for the user, where the recommendation is pending delivery at an appropriate time. The recommendation may be stored within the RAM 170.

At step 640, the recommendation delivery module 194, under execution of the processor 105 of the tablet device 101 -B, performs the step of receiving the device preferences 197 (i.e., defining preference ratings) for each of the plurality of electronic devices 101. The device preferences are based on a task to be recommended by the associated recommendation received at step 630. As described above, each of the preference ratings of the device preferences received at step 640 are configured for defining preference of the user for receiving the recommendation received at step 630 on a corresponding one of the electronic devices 101 (e.g., the tablet device 101-B). Also at step 640, the recommendation delivery module 194, under execution of the processor 105 of the tablet device 101-B, receives the timeliness profile 195 associated with the recommendation 193. As described above, the 5 timeliness profile 195 defines the relevance of delivering the recommendation over a period of time and, in particular, the change in relevance over the time period. The device preferences 197 and the timeliness profile 195 may be stored within the RAM 170 of the tablet device 101-B.

Then at step 650, the recommendation delivery module 194, under execution of the 0 processor 105, uses available information, including the usage profile 192, the device preferences 197 and the timeliness profiles (e.g., 195-1. 195-2), to determine a suitability rating for delivering the recommendation 193 to the tablet device 101-B (i.e., the current device) or to one of the other devices 101-A, 101-C or 101-D. For example, the user may use one of the other devices 101-A, 101-C or 101-D in the future. The suitability rating is 25 determined according to the usage profile 196. The determination of the suitability rating will be described in more detail below with reference to Fig. 7.

At step 660, if the processor 105 determines that the suitability rating for delivering the recommendation 193 to the current device 101-B, at the current point in time, is higher than for the other devices 101-A, 101-C and 101-D, then the method 600 proceeds to step 670. 30 Otherwise, the method 600 returns to step 610. In this instance, the recommendation delivery module 194 withholds delivery of the recommendation 193 and waits for a better time. The recommendation delivery module 194 may also select another one of the devices 101-A, 101-C and 101-D on which to deliver the recommendation 193. For example, the suitability rating 670914v 1 (P042054_Speci_As Filed) - 17- 2012227156 17 Sep 2012 associated with one of the other devices 101-A, 101-C and 101-D may be potentially higher due to one of the other devices 101-A, 101-C and 101-D being more preferred by the user for receiving the recommendation 193.

As another example, the recommendation delivery module 194 may determine at step 660 that the timeliness profile (i.e., defining a timeliness function) indicates that relevance of the recommendation will increase closer to the event. In this instance, again, the recommendation delivery module 194 withholds delivery of the recommendation 193 and waits for a better time.

The suitability rating, S, for a particular one of the electronic devices 101 is a function of device preference 197, probability of a device being used and timeliness of the recommendation being delivered in accordance with Equation (2), as follows: s = Dr„, x D„„„ x R (2) 5 where S represents suitability rating, Dpre/ represents device preference for the recommendation to be delivered, Dprob represents probability of the device being used at a particular point in time, and R represents the relevance of the recommendation according to the associated timeliness profile (e.g., 195-1, 195-2).

The values of all of the terms Dpref, Dpr0b, and R are in a scale between zero (0) and 0 one (1). When 5 is calculated for the current device, Dprob is always 1.0 as there is a 100% certainty that the device is being used.

At selecting step 670, the processor 105 performs the step of selecting the current electronic device (i.e., the tablet device 101-B in the present example) on which to deliver the recommendation 193. Also at step 670, the processor 105 delivers the recommendation 193 25 using the current electronic device 101-B. For example, the processor 105 may display the recommendation as a textual message on the display 114 of the tablet device 101-B. The recommendation 193 is delivered to the current electronic device 101-B at the current point in time. Accordingly, in the described method 600, the electronic device (e.g., the tablet device 101-B in the present example) on which to deliver the recommendation 193 is selected based 30 on a suitability rating of the selected electronic device and the timeliness profile associated with the recommendation. As described in further detail below, the electronic device (e.g., the tablet device 101-B in the present example) on which to deliver the recommendation 193 is 670914vl (P042054_Speci_As Filed) -18- 2012227156 17 Sep 2012 also selected based on predicted future use of one or more of the plurality of other devices 101-A, 101 -C and 101-D.

Fig. 7 is a graph 700 showing an example of suitability ratings determined for a user’s typical device usage sessions. The determined suitability ratings of Fig. 7 are based on the example usage profile 192 shown in Fig. 2, the example device preferences 197 shown in Fig. 4 for a photo book recommendation. The determined suitability ratings of Fig. 7 are also determined based on example timeliness function 720 as shown in Fig. 7. The line 720 shown in Fig. 7 represents relevance of delivering the recommendation.

As seen in Fig. 7, suitability rating 710 for delivering a photo book recommendation to ) the tablet device 101 -B on Thursday between 7:00AM and 7:30AM is therefore: S = DpKf x Dproh x /? = 0.8 x 0.95 χ 1.0 = 0.76

Similarly, suitability ratings may be determined for other device usage sessions according to the example usage profile 192 of Fig. 2 around a more relevant period (i.e., Monday to Friday) of the timeliness function example 720. In one arrangement, the 5 recommendation delivery module 194 uses the graph 700 plotting suitability ratings to determine, at step 650, a suitability rating for delivering the recommendation 193 to the tablet device 101 -B (i.e., the current device). The recommendation delivery module 194 may use the graph 700 for determining (or for predicting) if there is a better time for delivering a recommendation by comparing the suitability rating for delivering the recommendation at the 0 current point in time with other suitability ratings corresponding to future device usage sessions. For example, if the user is currently using the tablet device 101 -B during the period 7:00AM-7:30AM on Wednesday, as shown in Fig. 7, the suitability rating 730 will be (0.8 * 1.0 * 0.6) = 0.48 where Dprob is 1.0 for the current device (i.e., tablet device 101-B). In accordance with the example of Fig. 7, when comparing the current suitability rating with 25 other future suitability ratings, there is at least one potential session (i.e. Thursday 7:00AM-7:30AM), when the suitability rating 710 is higher. In the example, the recommendation will be withheld at step 660 for delivery at a better time in the future. In another example, if there is no potential device usage session with a higher suitability rating in the future, at step 660, then the method 600 proceeds to step 670 and the recommendation is delivered to the current 30 device (i.e., tablet device 101-B). Accordingly, the graph 700 comprises details for predicting use of each of the plurality of electronic devices 101. 6709l4v I (P042054_Speci_As Filed) - 19- 2012227156 17 Sep 2012

Industrial Applicability

The arrangements described are applicable to the computer and data processing industries and particularly for delivering recommendations.

The foregoing describes only some embodiments of the present invention, and modifications and/or changes can be made thereto without departing from the scope and spirit of the invention, the embodiments being illustrative and not restrictive.

In the context of this specification, the word “comprising” means “including principally but not necessarily solely” or “having” or “including”, and not “consisting only of’. Variations of the word "comprising", such as “comprise” and “comprises” have correspondingly varied meanings. 670914v 1 (P042054_Speci_As Filed)

Claims (15)

1. CLAIMS:

   1. A method of selecting an electronic device for delivering a recommendation, said method comprising: receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; receiving a timeliness profile associated with the recommendation, said timeliness profile defining a degree of relevance of delivering the recommendation with respect to an event over a period of time, the timeliness profile being stored in a second memory of the computer of the computer device; selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the first memory and on a degree of relevance of delivering the recommendation with respect to the event at said particular point in time determined by retrieving the corresponding degree of relevance from the second memory where the timeliness profile associated with the recommendation is stored.
2. 2. The method according to claim 1, further comprising receiving a usage profile predicting use of each of the plurality of devices.
3. 3. The method according to claim 2, wherein selection of the electronic device is also based on predicted future use of one or more of the plurality of devices.
4. 4. The method according to claim 1, further comprising capturing a usage history of an electronic device.
5. 5. The method according to claim 2, wherein the usage profile is determined from the captured usage history.
6. 6. The method according to claim 1, wherein the electronic device is a mobile phone.
7. 7. The method according to claim 1, wherein the electronic device is a portable media player.
8. 8. The method according to claim 1, wherein the electronic device is a digital camera.
9. 9. The method according to claim 1, wherein the electronic device is a computer.
10. 10. The method according to claim 1, wherein selecting one of said electronic devices on which to deliver the recommendation at a particular point in time is further based on a degree of relevance of delivering the recommendation to at least one other point in time in future determined using the timeliness profile associated with the recommendation.
11. 11. The method according to claim 10, wherein selecting one of said electronic devices on which to deliver the recommendation at a particular point in time is further based on likelihood of use of the selected device at the least one other point in time in future.
12. 12. The method according to claim 1, wherein the timeliness profile is based on the event related to the recommendation and efforts required to attend to the recommendation.
13. 13. A system for selecting an electronic device for delivering a recommendation, said system comprising: a memory for storing data and a computer program; a processor coupled to said memory for executing said computer program, said computer program comprising instructions for: receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; receiving a timeliness profile associated with the recommendation, said timeliness profile defining a degree of relevance of delivering the recommendation with respect to an event over a period of time, the timeliness profile being stored in a second memory of the computer device; selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the first memory and on a degree of relevance of delivering the recommendation with respect to the event at said particular point in time determined by retrieving the corresponding degree of relevance from the second memory where the timeliness profile associated with the recommendation is stored.
14. 14. An apparatus for selecting an electronic device for delivering a recommendation, said apparatus comprising: means for receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; means for receiving a timeliness profile associated with the recommendation, said timeliness profile defining a degree of relevance of delivering the recommendation with respect to an event over a period of time, the timeliness profile being stored in a second memory of the computer device; means for selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the first memory and on a degree of relevance of delivering the recommendation with respect to the event at said particular point in time determined by retrieving the corresponding degree of relevance from the second memory where the timeliness profile associated with the recommendation is stored.
15. 15. A computer readable medium having a computer program stored thereon for selecting an electronic device for delivering a recommendation, said program: code for receiving a rating for each of a plurality of electronic devices based on a task to be recommended, each of said ratings defining preference of a user for receiving the recommendation on a corresponding one of said electronic devices, the ratings being stored in a first memory of a computer device; code for receiving a timeliness profile associated with the recommendation, said timeliness profile defining relevance of delivering the recommendation with respect to an event over a period of time, the timeliness profile being stored in a second memory of the computer device; code for selecting one of said electronic devices on which to deliver the recommendation at a particular point in time based on the rating of the selected electronic device stored in the first memory and on a degree of relevance of delivering the recommendation with respect to the event at said particular point in time determined by retrieving the corresponding degree of relevance from the second memory where the timeliness profile associated with the recommendation is stored.